推薦提示詞

perfection style, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy

推薦反向提示詞

anime, cartoon, graphic, text, painting, crayon, graphite, abstract, deformed, mutated, disfigured, ugly breasts, tripod, camera, (censorship, worst quality, low quality, normal quality, lowres, low details, bad photo, bad photography, bad art:1.4), ugly, (watermark, signature, text font, username, error, glitch, logo, words, letters, censored, digits, autograph, trademark, name:1.2), (blur, blurry), morbid, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, JPEG artifacts, out of focus, duplicate, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3) (ugly hands, ugly anatomy, ugly body, ugly face, ugly teeth, ugly arms, ugly legs, deformities:1.3) ugly fingers, bad fingers, (((ugly nipples, bad nipples, deformed nipples))), (((Bad teeth, ugly teeth)))

推薦參數

samplers

DPM++ 3M SDE

steps

35

cfg

4 - 4.5

resolution

1024x1024

other models

perfection style (fd28810bd9a1), juggernautXL_v9Rundiffusionphoto2 (c9e3e68f89)

提示

Please read version info before using different versions such as Pony and Illustrious.

This model works best when combined with Detailed style XL (Hand focus + All in One) Detailed Perfection style extension.

You can use the model as an extra layer without any prompt when combined with other lora models.

Check additional asset models for hands and feet for better detail.

版本亮點

This style has been trained on high quality photos and embedded to produce anything "perfect". (Theoretically speaking no such thing is perfect but pretty much close to perfection)

You can follow example prompt photos as a guide line.

Model is very well balanced that can be combined with any other lora models. (You can always play with weight)

Please keep in mind model is not a 100 percent perfect. (It's goal is to get thigs close to or near perfection)

In addition, you can use the model as an extra layer without any prompt when combined with any other lora model(s).

創作者贊助

UpdatePlease if you see any of my models somewhere else report or let me know! Thnx

Trained on base model xl 1.0 + F1D

Update: SD1.5 version added.

Update: Pony version added! (Please read version info. before using it)

Update: Illustrious version added

Please read info. (Box on right) about this version.

This model will work best when combined with Detailed style XL (Hand focus + All in One) "Detailed Perfection style extension"

Works well with juggernaut model and realistic stock photo model and pretty much any other model.

In addition, you can use the model as an extra layer without any prompt when combined with any other lora model(s).

Also you can check hands asset model and feet asset model

Feedback and ratings are much appreciated.

Other models to check:

Skin Tone (Cinematic Photography) Style XL (Human skin color)

Realistic Skin Texture style XL (Detailed Skin)

Facial Expressions (detailed emotions) style XL

Perfect Eyes (Variaty of sclera) XL

上一個
Flux.1-Dev Hyper NF4 + Flux.1-Dev BNB NF4 + Flux.1-Schnell BNB NF4 - Flux.1-Dev BNB NF4 v2
下一個
Artsy Vibe - v1 - FP8

模型詳情

模型類型

LORA

基礎模型

SDXL 1.0

模型版本

Perfection SDXL v1.0

模型雜湊值

14d83e2b8c

訓練詞彙

perfection style
perfection
perfect

創作者

討論

log in以發表評論。

模型合集 - Detailed Perfection style (Hands + Feet + Face + Body + All in one) XL + F1D + SD1.5 + Pony + Illu